Get the latest tech news

Processing Strings 109x Faster Than Nvidia on H100

I’ve just shipped StringZilla v4, the first CUDA-capable release of my SIMD-first string processing library. Which in English means that it is now fast not only on CPUs, but also on GPUs! I’ve wanted to add ROCm-acceleration for AMD GPUs 🤦‍♂️ I’ve wanted to include a parallel multi-pattern search algorithm 🤦‍♂️ I’ve wanted to publish it back in December 2024 🤦‍♂️ So not everything went to plan, but “StringZilla 4 CUDA” is finally here, bringing 500+ GigaCUPS of edit-distance calculations in a pip install-able package, and a few more tricks up its sleeve, aimed at large-scale Information Retrieval, Databases and Datalake systems, as well as Bioinformatics workloads. All under a permissive Apache 2.0 open-source license, free for commercial use. So in this post, we’ll cover some of the most interesting parts of this release, including:

So not everything went to plan, but “StringZilla 4 CUDA” is finally here, bringing 500+ GigaCUPS of edit-distance calculations in a pip install-able package, and a few more tricks up its sleeve, aimed at large-scale Information Retrieval, Databases and Datalake systems, as well as Bioinformatics workloads. It later added support for little- & big-endian platforms; several generations of AVX-512 on x86, Arm NEON, SVE, and SVE2 extensions; dynamic dispatch; and first-party bindings for Python, Rust, JavaScript, and even Swift, translating the underlying C99 implementation. USearch, my search engine, uses 40-bit integers to identify entries - a non-standard size chosen to balance memory efficiency with a large enough address space to fit 1 trillion of vectors on 1 machine.

Get the Android app